crewai
Warn
Audited by Snyk on Aug 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a runtime workflow where a “researcher” agent is configured with external search/web tools (SerperDevTool/WebsiteSearchTool) that can ingest arbitrary outsider-authored text from search results or scraped web pages without requiring the user to select a specific trusted item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata